{
  "@context": "https://schema.org",
  "@id": "https://aggr.aymericbeaumet.com/items/ampcode-com/2026-09-29-plaid-speed/#webpage",
  "@type": [
    "WebPage",
    "ArchiveComponent"
  ],
  "articleBody": "Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token.\n\nOpen the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past **Fast** to **Plaid**.\n\n![The mode dial with high selected and the speed switch set to Plaid, showing the red 6× cost indicator](https://static.ampcode.com/news/plaid-new-thread-toggle-6x-final-20260929.avif)\n\nPlaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.\n",
  "authors": [],
  "captured_at": "2026-10-03T23:09:50.514863041+00:00",
  "category": "programming",
  "content_html": "<p>Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token.</p>\n<p>Open the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past <strong>Fast</strong> to <strong>Plaid</strong>.</p>\n<p><picture class=\"article-picture article-picture-fallback\" style=\"--image-ratio:16 / 9\"><img src=\"https://static.ampcode.com/news/plaid-new-thread-toggle-6x-final-20260929.avif\" alt=\"The mode dial with high selected and the speed switch set to Plaid, showing the red 6× cost indicator\" loading=\"eager\" decoding=\"async\" fetchpriority=\"high\" referrerpolicy=\"no-referrer\" class=\"progressive-image\"></picture></p>\n<p>Plaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.</p>\n",
  "content_markdown": "Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token.\n\nOpen the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past **Fast** to **Plaid**.\n\n![The mode dial with high selected and the speed switch set to Plaid, showing the red 6× cost indicator](https://static.ampcode.com/news/plaid-new-thread-toggle-6x-final-20260929.avif)\n\nPlaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.\n",
  "dateCreated": "2026-10-03T23:09:50.514863041+00:00",
  "date_created": "2026-09-29T00:00:00+00:00",
  "date_modified": "2026-09-29T00:00:00+00:00",
  "date_published": "2026-09-29T00:00:00+00:00",
  "description": "Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token. Open the mode picker in the new thread dialog, choose a…",
  "external_url": "https://ampcode.com/news/plaid-mode",
  "git": {
    "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e",
    "path": "items/ampcode-com/2026/09/2026-09-29-plaid-speed.md",
    "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/ampcode-com/2026/09/2026-09-29-plaid-speed.md"
  },
  "id": "urn:aggr:item:b5213e4066cf9162fbea7728765ed25bc83ae55c",
  "isBasedOn": {
    "@id": "https://ampcode.com/news/plaid-mode"
  },
  "mainEntity": {
    "@id": "https://ampcode.com/news/plaid-mode",
    "@type": "CreativeWork",
    "archivedAt": {
      "@id": "https://aggr.aymericbeaumet.com/items/ampcode-com/2026-09-29-plaid-speed/#webpage"
    },
    "dateModified": "2026-09-29T00:00:00+00:00",
    "datePublished": "2026-09-29T00:00:00+00:00",
    "headline": "Plaid Speed",
    "timeRequired": "PT1M",
    "url": "https://ampcode.com/news/plaid-mode",
    "wordCount": 116
  },
  "name": "Archived snapshot: Plaid Speed",
  "preview": null,
  "reading_minutes": 1,
  "replicated_at": null,
  "source": "ampcode-com",
  "source_name": "Amp News",
  "summary": "Amp now supports Plaid speed for modes that use GPT-6 Astra. Plaid uses OpenAI's ultrafast speed tier, which enables inference requests to run up to 6× faster, with 6× cost per token. Open the mode picker in the new thread dialog, choose a mode that uses GPT-6 Astra (e.g., the default High mode), and move the speed switch past Fast to Plaid. Plaid currently works with Amp-provided inference only, as OpenAI does not yet support ultrafast for linked ChatGPT subscriptions. When Plaid is activated, subagents and non-Plaid-enabled model inference will fall back to fast or standard speed. Like fast mode, Plaid can be toggled on or off for an existing thread.",
  "tags": [],
  "temporalCoverage": "2026-10-03T23:09:50.514863041+00:00",
  "title": "Plaid Speed",
  "url": "https://aggr.aymericbeaumet.com/items/ampcode-com/2026-09-29-plaid-speed/",
  "word_count": 116
}